Activity
From 08/08/2022 to 09/06/2022
09/06/2022
- 08:44 PM Backport #56462: pacific: mds: crash due to seemingly unrecoverable metadata error
- Backport Bot wrote:
> https://github.com/ceph/ceph/pull/47433
merged - 08:43 PM Backport #56449: pacific: pjd failure (caused by xattr's value not consistent between auth MDS an...
- Backport Bot wrote:
> https://github.com/ceph/ceph/pull/47056
merged - 05:56 PM Feature #51716 (Resolved): Add option in `fs new` command to start rank 0 in failed state
- 05:55 PM Backport #52680 (Resolved): pacific: Add option in `fs new` command to start rank 0 in failed state
- 04:09 PM Backport #57058: pacific: mgr/volumes: Handle internal metadata directories under '/volumes' prop...
- Backport Bot wrote:
> https://github.com/ceph/ceph/pull/47512
merged - 01:08 PM Bug #50387 (Duplicate): client: fs/snaps failure
- Duplicate of https://tracker.ceph.com/issues/54460
- 12:34 PM Bug #57446 (In Progress): qa: test_subvolume_snapshot_info_if_orphan_clone fails
- 12:29 PM Bug #57446 (Pending Backport): qa: test_subvolume_snapshot_info_if_orphan_clone fails
- The test test_subvolume_snapshot_info_if_orphan_clone failed in the following test run
http://pulpito.front.sepia.... - 12:26 PM Backport #56712 (Resolved): pacific: mds: standby-replay daemon always removed in MDSMonitor::pre...
- 11:57 AM Backport #57283 (In Progress): quincy: cephfs-top:addition of filesystem menu(improving GUI)
- 08:17 AM Backport #57156 (Resolved): quincy: cephfs-top: wrong/infinitely changing wsp values
- 08:11 AM Bug #53126: In the 5.4.0 kernel, the mount of ceph-fuse fails
- Hi Jiang,
The fix for this is available in quincy (17.*). Do you mind upgrading your cluster? - 07:24 AM Bug #57084: Permissions of the .snap directory do not inherit ACLs
- Venky Shankar wrote:
> Is this the user-space or the kernel client?
It happens with kernel 5.15 and ceph-fuse 1... - 06:18 AM Bug #57084: Permissions of the .snap directory do not inherit ACLs
- Thanks for the detailed report, Robert. This sounds like a bug.
Is this the user-space or the kernel client? - 06:34 AM Bug #57205: Test failure: test_subvolume_group_ls_filter_internal_directories (tasks.cephfs.test_...
- The snapshot removal has failed because it had pending clones. Please see below....
- 06:33 AM Bug #57205 (In Progress): Test failure: test_subvolume_group_ls_filter_internal_directories (task...
- 06:22 AM Bug #54701 (Resolved): crash: void Server::set_trace_dist(ceph::ref_t<MClientReply>&, CInode*, CD...
- 06:21 AM Backport #55933 (Resolved): quincy: crash: void Server::set_trace_dist(ceph::ref_t<MClientReply>&...
- 06:21 AM Backport #55932 (Resolved): pacific: crash: void Server::set_trace_dist(ceph::ref_t<MClientReply>...
- 06:21 AM Bug #53857 (Resolved): qa: fs:upgrade test fails mds count check
- 06:20 AM Bug #51964: qa: test_cephfs_mirror_restart_sync_on_blocklist failure
- Lowering priority -- this is an issue with the test case rather than a bug in cephfs-mirror.
- 06:19 AM Bug #52487 (Resolved): qa: Test failure: test_deep_split (tasks.cephfs.test_fragment.TestFragment...
- 05:36 AM Bug #51589 (Resolved): mds: crash when journaling during replay
- 02:19 AM Backport #57041 (Resolved): pacific: pybind/mgr/volumes: interface to check the presence of subvo...
09/05/2022
- 02:11 PM Backport #57439 (In Progress): pacific: client: track (and forward to MDS) average read/write/met...
- 01:24 PM Backport #57439 (Resolved): pacific: client: track (and forward to MDS) average read/write/metada...
- https://github.com/ceph/ceph/pull/47978
- 01:54 PM Bug #57411: mutiple mds crash seen while running db workloads with regular snapshots and journal ...
- ...
- 01:02 PM Bug #57411: mutiple mds crash seen while running db workloads with regular snapshots and journal ...
- Thanks for reproducing this, Hemanth. This has been seen in the past but there were no logs to debug. Could you pleas...
- 01:49 PM Backport #57440 (In Progress): quincy: client: track (and forward to MDS) average read/write/meta...
- 01:24 PM Backport #57440 (Resolved): quincy: client: track (and forward to MDS) average read/write/metadat...
- https://github.com/ceph/ceph/pull/47977
- 01:17 PM Feature #48619 (Pending Backport): client: track (and forward to MDS) average read/write/metadata...
- 12:49 PM Bug #56261: crash: Migrator::import_notify_abort(CDir*, std::set<CDir*, std::less<CDir*>, std::al...
- Since there's any reference to an assertion failure in the backtrace, I had to resort to code walk-through.
Nothing ... - 12:33 PM Fix #51177 (In Progress): pybind/mgr/volumes: investigate moving calls which may block on libceph...
- 10:00 AM Backport #57261: pacific: standby-replay mds is removed from MDSMap unexpectedly
- Waiting for https://github.com/ceph/ceph/pull/47282 to be merged in pacific.
- 09:26 AM Fix #52591 (Resolved): mds: mds_oft_prefetch_dirfrags = false is not qa tested
- 09:14 AM Backport #55931 (In Progress): pacific: client: allow overwrites to files with size greater than ...
- 09:13 AM Backport #55930 (In Progress): quincy: client: allow overwrites to files with size greater than t...
- 08:56 AM Bug #57206: ceph_test_libcephfs_reclaim crashes during test
- Tamar,
Were you able to go through the changes for the rgw fix here: https://github.com/ceph/ceph/pull/47504 to se... - 08:07 AM Bug #54760: crash: void CDir::try_remove_dentries_for_stray(): assert(dn->get_linkage()->is_null())
- I think https://github.com/ceph/ceph/pull/46331 would mitigate this issue, however, the unlink and openc are from dif...
- 08:04 AM Bug #54760: crash: void CDir::try_remove_dentries_for_stray(): assert(dn->get_linkage()->is_null())
- This looks like a race between an unlink and openc (open w/ O_CREAT) in the MDS -- the unlink RPC projects the old an...
- 12:35 AM Backport #57253 (Resolved): quincy: Restore the AT_NO_ATTR_SYNC define in libcephfs
09/03/2022
- 02:51 PM Backport #57253: quincy: Restore the AT_NO_ATTR_SYNC define in libcephfs
- Backport Bot wrote:
> https://github.com/ceph/ceph/pull/47861
merged - 02:50 PM Backport #57264: quincy: pybind/mgr/volumes: add basic introspection
- Backport Bot wrote:
> https://github.com/ceph/ceph/pull/47768
merged
09/02/2022
- 10:10 PM Backport #57370: quincy: standby-replay mds is removed from MDSMap unexpectedly
- Backport Bot wrote:
> https://github.com/ceph/ceph/pull/47902
merged - 05:37 PM Bug #57411: mutiple mds crash seen while running db workloads with regular snapshots and journal ...
- mds logs are copied here - http://magna002.ceph.redhat.com/ceph-qe-logs/hemanth/ceph_tracker/57411/
- 05:34 PM Bug #57411 (Duplicate): mutiple mds crash seen while running db workloads with regular snapshots ...
While the pgbench workloads are on with snapshots being taken after each run and with regular journal flush.
I ...- 03:27 PM Backport #57156: quincy: cephfs-top: wrong/infinitely changing wsp values
- Backport Bot wrote:
> https://github.com/ceph/ceph/pull/47648
merged - 12:36 PM Backport #57395 (Resolved): pacific: crash: int Client::_do_remount(bool): abort
- https://github.com/ceph/ceph/pull/48108
- 12:36 PM Backport #57394 (Resolved): quincy: crash: int Client::_do_remount(bool): abort
- https://github.com/ceph/ceph/pull/48107
- 12:35 PM Backport #57393 (Resolved): pacific: client: abort the client daemons when we couldn't invalidate...
- https://github.com/ceph/ceph/pull/48109
- 12:35 PM Backport #57392 (Resolved): quincy: client: abort the client daemons when we couldn't invalidate ...
- https://github.com/ceph/ceph/pull/48110
- 12:25 PM Bug #56476 (Resolved): qa/suites: evicted client unhandled in 4-compat_client.yaml
- 12:25 PM Bug #57126 (Pending Backport): client: abort the client daemons when we couldn't invalidate the d...
- 12:25 PM Bug #56249 (Pending Backport): crash: int Client::_do_remount(bool): abort
- 06:08 AM Bug #55710 (Resolved): cephfs-shell: exit code unset when command has missing argument
- The PR was merged by Venky few months ago - https://github.com/ceph/ceph/pull/46337#event-6657873439.
- 06:04 AM Bug #55719 (Resolved): test_cephfs_shell: temporary files cause tests to fail with vstart_runner.py
- The PR was merged few months ago.
- 01:37 AM Backport #56448 (Resolved): quincy: pjd failure (caused by xattr's value not consistent between a...
09/01/2022
- 11:05 PM Backport #56448: quincy: pjd failure (caused by xattr's value not consistent between auth MDS and...
- Backport Bot wrote:
> https://github.com/ceph/ceph/pull/47057
merged - 01:50 PM Backport #57370 (In Progress): quincy: standby-replay mds is removed from MDSMap unexpectedly
- 01:11 PM Backport #57370 (Resolved): quincy: standby-replay mds is removed from MDSMap unexpectedly
- https://github.com/ceph/ceph/pull/47902
- 01:14 PM Bug #54501: libcephfs: client needs to update the mtime and change attr when snaps are created an...
- Dhairya, PTAL.
- 01:13 PM Bug #57205: Test failure: test_subvolume_group_ls_filter_internal_directories (tasks.cephfs.test_...
- Kotresh, PTAL.
- 01:01 PM Backport #57262 (Rejected): octopus: standby-replay mds is removed from MDSMap unexpectedly
- 10:02 AM Bug #57154 (In Progress): kernel/fuse client using ceph ID with uid restricted MDS caps cannot up...
- 07:42 AM Backport #57242 (In Progress): quincy: mgr/volumes: Clone operations are failing with Assertion E...
- 06:58 AM Fix #51177: pybind/mgr/volumes: investigate moving calls which may block on libcephfs into anothe...
- Discussion Summary with Patrick
1. Have a thread for each module to execute module commands. Since the finisher th... - 06:24 AM Backport #57057 (Resolved): quincy: mgr/volumes: Handle internal metadata directories under '/vol...
- 06:21 AM Bug #56632 (Fix Under Review): qa: test_subvolume_snapshot_clone_quota_exceeded fails CommandFail...
- 02:37 AM Backport #57363 (In Progress): pacific: ffsb.sh test failure
- 02:13 AM Backport #57363 (Resolved): pacific: ffsb.sh test failure
- https://github.com/ceph/ceph/pull/47891
- 02:37 AM Backport #57239 (In Progress): pacific: ceph-fs crashes on getfattr
- 02:18 AM Backport #57362 (In Progress): quincy: ffsb.sh test failure
- 02:13 AM Backport #57362 (Resolved): quincy: ffsb.sh test failure
- https://github.com/ceph/ceph/pull/47890
- 02:17 AM Backport #57240 (In Progress): quincy: ceph-fs crashes on getfattr
- 02:06 AM Bug #54461 (Pending Backport): ffsb.sh test failure
- 01:22 AM Bug #57361 (Triaged): cephfs: rbytes seems not work correctly
- I had two client with the **rbytes** enabled, one is kclient and another is ceph-fuse client. In kclient after I crea...
08/31/2022
- 08:46 PM Bug #57359 (Resolved): mds/Server: -ve values cause unexpected client eviction while handling cli...
- I found this issue while writing tests for PR-47080 where sending negative value for reclaim flag caused tests to fre...
- 02:28 PM Backport #57112: quincy: Intermittent ParsingError failure in mgr/volumes module during "clone c...
- Backport Bot wrote:
> https://github.com/ceph/ceph/pull/47747
merged - 02:28 PM Backport #57200: quincy: snap_schedule: replace .snap with the client configured snap dir name
- Backport Bot wrote:
> https://github.com/ceph/ceph/pull/47734
merged - 12:49 PM Bug #57206: ceph_test_libcephfs_reclaim crashes during test
- The same crash reported for rgw - https://tracker.ceph.com/issues/57050
I"ll go over it to get the details. - 07:31 AM Bug #57344 (Fix Under Review): libcephfs: incorrectly showing the size for snapdirs when stating ...
- 07:28 AM Bug #57344 (Pending Backport): libcephfs: incorrectly showing the size for snapdirs when stating ...
- There are 4 snapshots under the **/mnt/kcephfs/.snap/**:...
08/30/2022
- 10:00 AM Backport #57274 (In Progress): pacific: mgr/stats: missing clients in perf stats command output.
- 09:39 AM Backport #57273 (In Progress): quincy: mgr/stats: missing clients in perf stats command output.
- 07:26 AM Backport #57252 (In Progress): pacific: Restore the AT_NO_ATTR_SYNC define in libcephfs
- 02:54 AM Backport #57253 (In Progress): quincy: Restore the AT_NO_ATTR_SYNC define in libcephfs
- 02:31 AM Backport #56055 (Resolved): quincy: crash: uint64_t CephFuse::Handle::fino_snap(uint64_t): assert...
08/29/2022
- 03:13 PM Backport #56055: quincy: crash: uint64_t CephFuse::Handle::fino_snap(uint64_t): assert(stag_snap_...
- Backport Bot wrote:
> https://github.com/ceph/ceph/pull/46948
merged - 12:49 PM Bug #57280 (Triaged): qa: tasks/kernel_cfuse_workunits_untarbuild_blogbench fails - Failed to fet...
- 10:39 AM Backport #57330 (In Progress): quincy: Test failure: test_client_metrics_and_metadata (tasks.ceph...
- 10:33 AM Backport #57330 (Resolved): quincy: Test failure: test_client_metrics_and_metadata (tasks.cephfs....
- https://github.com/ceph/ceph/pull/47820
- 10:38 AM Backport #57331 (In Progress): pacific: Test failure: test_client_metrics_and_metadata (tasks.cep...
- 10:33 AM Backport #57331 (Resolved): pacific: Test failure: test_client_metrics_and_metadata (tasks.cephfs...
- https://github.com/ceph/ceph/pull/47851
- 10:21 AM Bug #55861 (Pending Backport): Test failure: test_client_metrics_and_metadata (tasks.cephfs.test_...
08/28/2022
- 09:20 AM Bug #57206: ceph_test_libcephfs_reclaim crashes during test
- I"ve used https://github.com/ceph/ceph/blob/main/src/script/ceph-debug-docker.sh for deploying the build on container...
08/27/2022
- 11:16 AM Bug #50840 (Resolved): mds: CephFS kclient gets stuck when getattr() on a certain file
- 11:16 AM Backport #51202 (Resolved): octopus: mds: CephFS kclient gets stuck when getattr() on a certain file
08/26/2022
- 06:30 PM Bug #51282: pybind/mgr/mgr_util: .mgr pool may be created too early causing spurious PG_DEGRADED ...
- /a/yuriw-2022-08-22_20:21:58-rados-wip-yuri11-testing-2022-08-22-1005-distro-default-smithi/6986324
Description: r... - 06:29 PM Bug #55825 (Duplicate): cluster [WRN] Health check failed: Degraded data redundancy: 1 pg degrade...
- 05:33 PM Backport #57277 (In Progress): pacific: mgr/stats: 'perf stats' command shows incorrect output wi...
- 05:30 PM Backport #57279 (In Progress): pacific: mgr/stats: add fs_name as field in perf stats command output
- 05:24 PM Backport #57276 (In Progress): quincy: mgr/stats: 'perf stats' command shows incorrect output wit...
- 05:21 PM Backport #57278 (In Progress): quincy: mgr/stats: add fs_name as field in perf stats command output
- 02:48 PM Bug #57210: NFS client unable to see newly created files when listing directory contents in a FS ...
- Also worth noting is that as per https://bugzilla.redhat.com/show_bug.cgi?id=2118263#c11 , this is a regression in th...
- 12:36 PM Bug #57210: NFS client unable to see newly created files when listing directory contents in a FS ...
- Disabled caching to match the original BZ setup https://bugzilla.redhat.com/show_bug.cgi?id=2118263#c2...
- 01:16 PM Bug #56414 (Resolved): mounting subvolume shows size/used bytes for entire fs, not subvolume
- 09:07 AM Bug #57072 (Fix Under Review): Quincy 17.2.3 pybind/mgr/status: assert metadata failed
- 07:56 AM Feature #56140 (Resolved): cephfs: tooling to identify inode (metadata) corruption
- 06:13 AM Bug #56988: mds: memory leak suspected
- I have attached the current "ceph tell mds.<fs_name>:0 perf dump" log files.
Files with the name:
ceph_mds_perf_<... - 01:22 AM Bug #53597 (Resolved): mds: FAILED ceph_assert(dir->get_projected_version() == dir->get_version())
- 01:22 AM Backport #55928 (Resolved): quincy: mds: FAILED ceph_assert(dir->get_projected_version() == dir->...
- 01:20 AM Bug #56010 (Resolved): xfstests-dev generic/444 test failed
- 01:20 AM Backport #56464 (Resolved): quincy: xfstests-dev generic/444 test failed
- 01:14 AM Backport #56461 (Resolved): quincy: mds: crash due to seemingly unrecoverable metadata error
08/25/2022
- 10:06 PM Bug #57210: NFS client unable to see newly created files when listing directory contents in a FS ...
- Greg Farnum wrote:
> I wonder if the real difference here is not the cloned subvolume, but whether the mount point h... - 08:32 PM Backport #56461: quincy: mds: crash due to seemingly unrecoverable metadata error
- Backport Bot wrote:
> https://github.com/ceph/ceph/pull/47432
merged - 08:29 PM Backport #56464: quincy: xfstests-dev generic/444 test failed
- Backport Bot wrote:
> https://github.com/ceph/ceph/pull/47058
merged - 07:21 PM Bug #57280: qa: tasks/kernel_cfuse_workunits_untarbuild_blogbench fails - Failed to fetch package...
- Created a new Tracker for Cephadm, but marked a relation to this tracker.
- 07:12 PM Bug #57280: qa: tasks/kernel_cfuse_workunits_untarbuild_blogbench fails - Failed to fetch package...
- Several occurrences with cephadm tests on this run, such as:
/a/yuriw-2022-08-17_19:34:54-rados-wip-yuri7-testing-... - 05:53 PM Bug #57285 (Won't Fix): mds: removing data pool doesn't dissociate the pool from the cephfs appli...
- https://github.com/ceph/ceph/pull/47801#issuecomment-1227520097
- 05:38 PM Bug #57299 (Fix Under Review): qa: test_dump_loads fails with JSONDecodeError
- 05:25 PM Bug #57299 (Pending Backport): qa: test_dump_loads fails with JSONDecodeError
- @tasks.cephfs.test_admin.TestAdminCommandDumpLoads.test_dump_loads@ fails with @JSONDecodeError@. Traceback -
<pre... - 03:17 PM Backport #55928: quincy: mds: FAILED ceph_assert(dir->get_projected_version() == dir->get_version())
- Backport Bot wrote:
> https://github.com/ceph/ceph/pull/47181
merged - 03:14 PM Backport #57057: quincy: mgr/volumes: Handle internal metadata directories under '/volumes' prope...
- Backport Bot wrote:
> https://github.com/ceph/ceph/pull/47511
merged - 01:11 PM Fix #57295 (Fix Under Review): qa: remove RHEL from job matrix
- 01:08 PM Fix #57295 (Rejected): qa: remove RHEL from job matrix
- The last few months it has become a frequent source of avoidable problems.
- 12:30 PM Feature #55463 (Duplicate): cephfs-top: allow users to chose sorting order
- Marking this as duplicate of https://tracker.ceph.com/issues/55121 (that tracker has more context/discussions).
- 12:30 PM Feature #55121: cephfs-top: new options to limit and order-by
- Neeraj is working on this.
- 05:23 AM Feature #55197 (In Progress): cephfs-top: make cephfs-top display scrollable like top
- Venky Shankar wrote:
> Jos, I presume that you are working on this feature?
Yes. - 05:19 AM Feature #55197: cephfs-top: make cephfs-top display scrollable like top
- Jos, I presume that you are working on this feature?
08/24/2022
- 01:55 PM Fix #51177: pybind/mgr/volumes: investigate moving calls which may block on libcephfs into anothe...
- Spoke to Kotersh today - we may want to introduce an async command execution interface in plugins that the finisher t...
- 11:46 AM Bug #57285 (Won't Fix): mds: removing data pool doesn't dissociate the pool from the cephfs appli...
- ...
- 09:04 AM Bug #57072: Quincy 17.2.3 pybind/mgr/status: assert metadata failed
- cld slnt wrote:
> Venky Shankar wrote:
> > Could you provide more info on how you ran into this. A reproducer would... - 08:34 AM Bug #57072: Quincy 17.2.3 pybind/mgr/status: assert metadata failed
- Venky Shankar wrote:
> Could you provide more info on how you ran into this. A reproducer would really help (or at l... - 08:09 AM Bug #57280: qa: tasks/kernel_cfuse_workunits_untarbuild_blogbench fails - Failed to fetch package...
- It's ubuntu 22.04 Jammy JellyFish. The 'sha1' for client.0 is 'None', hence the failure. The client.0 is 'ceph-fuse'...
- 07:09 AM Bug #57280 (Resolved): qa: tasks/kernel_cfuse_workunits_untarbuild_blogbench fails - Failed to fe...
- Seen in multiple runs:
https://pulpito.ceph.com/yuriw-2022-08-22_21:15:31-fs-wip-yuri7-testing-2022-08-17-0943-quinc... - 08:09 AM Backport #57283 (Resolved): quincy: cephfs-top:addition of filesystem menu(improving GUI)
- https://github.com/ceph/ceph/pull/47820
- 08:09 AM Backport #57282 (Resolved): pacific: cephfs-top:addition of filesystem menu(improving GUI)
- https://github.com/ceph/ceph/pull/47998
- 08:09 AM Backport #57281 (In Progress): quincy: mds/MDBalancer: add an arg to limit depth when dump loads ...
- https://github.com/ceph/ceph/pull/54188
- 08:08 AM Feature #54978 (Pending Backport): cephfs-top:addition of filesystem menu(improving GUI)
- 08:01 AM Feature #56058 (Pending Backport): mds/MDBalancer: add an arg to limit depth when dump loads for ...
- 05:54 AM Backport #57279 (Resolved): pacific: mgr/stats: add fs_name as field in perf stats command output
- https://github.com/ceph/ceph/pull/47851
- 05:54 AM Backport #57278 (Resolved): quincy: mgr/stats: add fs_name as field in perf stats command output
- https://github.com/ceph/ceph/pull/47820
- 05:54 AM Backport #57277 (Resolved): pacific: mgr/stats: 'perf stats' command shows incorrect output with ...
- https://github.com/ceph/ceph/pull/47851
- 05:54 AM Backport #57276 (Resolved): quincy: mgr/stats: 'perf stats' command shows incorrect output with n...
- https://github.com/ceph/ceph/pull/47820
- 05:44 AM Bug #56169 (Pending Backport): mgr/stats: 'perf stats' command shows incorrect output with non-ex...
- 05:43 AM Bug #56162 (Pending Backport): mgr/stats: add fs_name as field in perf stats command output
- 04:51 AM Backport #57274 (Resolved): pacific: mgr/stats: missing clients in perf stats command output.
- https://github.com/ceph/ceph/pull/47866
- 04:51 AM Backport #57273 (Resolved): quincy: mgr/stats: missing clients in perf stats command output.
- https://github.com/ceph/ceph/pull/47820
- 04:20 AM Bug #56483 (Pending Backport): mgr/stats: missing clients in perf stats command output.
- 01:11 AM Bug #56988 (Need More Info): mds: memory leak suspected
- 01:11 AM Bug #56988: mds: memory leak suspected
- If you could capture...
- 12:49 AM Backport #56465 (Resolved): pacific: xfstests-dev generic/444 test failed
- 12:49 AM Backport #55929 (Resolved): pacific: mds: FAILED ceph_assert(dir->get_projected_version() == dir-...
08/23/2022
- 06:57 PM Backport #57263 (In Progress): pacific: pybind/mgr/volumes: add basic introspection
- 04:07 PM Backport #57263 (Resolved): pacific: pybind/mgr/volumes: add basic introspection
- https://github.com/ceph/ceph/pull/47769
- 06:17 PM Backport #57264 (In Progress): quincy: pybind/mgr/volumes: add basic introspection
- 04:07 PM Backport #57264 (Resolved): quincy: pybind/mgr/volumes: add basic introspection
- https://github.com/ceph/ceph/pull/47768
- 05:49 PM Bug #57249 (Fix Under Review): mds: damage table only stores one dentry per dirfrag
- 12:43 PM Bug #57249 (Resolved): mds: damage table only stores one dentry per dirfrag
- Some copy paste in
https://github.com/ceph/ceph/commit/c9cfaef104e9aaefad55583d7e54f8b4665904b3
caused DamageTa... - 04:07 PM Backport #57262 (Rejected): octopus: standby-replay mds is removed from MDSMap unexpectedly
- 04:07 PM Backport #57261 (Resolved): pacific: standby-replay mds is removed from MDSMap unexpectedly
- https://github.com/ceph/ceph/pull/48270
- 04:03 PM Feature #51434 (Pending Backport): pybind/mgr/volumes: add basic introspection
- 04:00 PM Bug #53811 (Pending Backport): standby-replay mds is removed from MDSMap unexpectedly
- 03:50 PM Bug #57154: kernel/fuse client using ceph ID with uid restricted MDS caps cannot update caps
- I think we need to look at session->check_access() call in Locker::_do_cap_update() . During cap update, does the MDS...
- 02:27 PM Backport #55929: pacific: mds: FAILED ceph_assert(dir->get_projected_version() == dir->get_versio...
- Backport Bot wrote:
> https://github.com/ceph/ceph/pull/47180
merged - 02:26 PM Backport #56465: pacific: xfstests-dev generic/444 test failed
- Backport Bot wrote:
> https://github.com/ceph/ceph/pull/47059
merged - 02:11 PM Backport #57253 (Resolved): quincy: Restore the AT_NO_ATTR_SYNC define in libcephfs
- https://github.com/ceph/ceph/pull/47861
- 02:11 PM Backport #57252 (Resolved): pacific: Restore the AT_NO_ATTR_SYNC define in libcephfs
- https://github.com/ceph/ceph/pull/47862
- 02:09 PM Bug #56638 (Pending Backport): Restore the AT_NO_ATTR_SYNC define in libcephfs
- 12:20 PM Bug #57248 (Fix Under Review): qa: mirror tests should cleanup fs during unwind
- 12:10 PM Bug #57248 (Resolved): qa: mirror tests should cleanup fs during unwind
- https://pulpito.ceph.com/vshankar-2022-08-18_04:30:42-fs-wip-vshankar-testing1-20220818-082047-testing-default-smithi...
- 09:16 AM Bug #57244 (Fix Under Review): [WRN] : client.408214273 isn't responding to mclientcaps(revoke), ...
- 08:32 AM Bug #57244 (Resolved): [WRN] : client.408214273 isn't responding to mclientcaps(revoke), ino 0x10...
- This is from cu case and there is no more debug logs. It's so strange that the MDS is waiting for the revoking respon...
- 08:33 AM Bug #49434 (Duplicate): `client isn't responding to mclientcaps(revoke)` for hours
- 08:00 AM Backport #57242 (Resolved): quincy: mgr/volumes: Clone operations are failing with Assertion Error
- https://github.com/ceph/ceph/pull/47894
- 08:00 AM Backport #57241 (Resolved): pacific: mgr/volumes: Clone operations are failing with Assertion Error
- https://github.com/ceph/ceph/pull/47112
- 07:55 AM Bug #55976 (Pending Backport): mgr/volumes: Clone operations are failing with Assertion Error
- 07:52 AM Backport #57240 (Resolved): quincy: ceph-fs crashes on getfattr
- https://github.com/ceph/ceph/pull/47890
- 07:52 AM Backport #57239 (Resolved): pacific: ceph-fs crashes on getfattr
- https://github.com/ceph/ceph/pull/47891
- 07:52 AM Bug #56529 (Pending Backport): ceph-fs crashes on getfattr
- 07:14 AM Bug #57044: mds: add some debug logs for "crash during construction of internal request"
- Debug PR merged. Waiting for logs in test runs...
- 07:09 AM Bug #57205: Test failure: test_subvolume_group_ls_filter_internal_directories (tasks.cephfs.test_...
- Nikhil, PTAL.
- 07:07 AM Bug #57204: MDLog.h: 99: FAILED ceph_assert(!segments.empty())
- Patrick Donnelly wrote:
> ?
Yeh. Thx! - 04:56 AM Backport #57113 (In Progress): pacific: Intermittent ParsingError failure in mgr/volumes module ...
- 04:50 AM Backport #57112 (In Progress): quincy: Intermittent ParsingError failure in mgr/volumes module d...
08/22/2022
- 10:25 PM Bug #47643: mds: Segmentation fault in thread 7fcff3078700 thread_name:md_log_replay
- I've ran into a very similar issue to this one on @17.2.0@. I tried to upgrade MDS to @17.2.3 (dff484dfc9e19a9819f375...
- 08:42 PM Backport #56526: quincy: mds: src/mds/MDLog.cc: 283: FAILED ceph_assert(!mds->is_ any_replay())
- Backport Bot wrote:
> https://github.com/ceph/ceph/pull/47110
merged - 06:57 PM Backport #55385 (In Progress): quincy: mgr/snap_schedule: include timezone information in schedul...
- 06:49 PM Backport #57200 (In Progress): quincy: snap_schedule: replace .snap with the client configured sn...
- 03:01 PM Documentation #57062: Document access patterns that have good/pathological performance on CephFS
- Niklas Hambuechen wrote:
> Hi Venky, I'm using the kclient on Linux 5.10.88 in this cluster.
Thanks, Niklas. I'll... - 01:34 PM Documentation #57062: Document access patterns that have good/pathological performance on CephFS
- Hi Venky, I'm using the kclient on Linux 5.10.88 in this cluster.
- 01:22 PM Documentation #57062: Document access patterns that have good/pathological performance on CephFS
- Hi Niklas,
Do you see this behavior with user-space and kclient? - 01:36 PM Feature #56643: scrub: add one subcommand or option to add the missing objects back
- Venky Shankar wrote:
> Xiubo Li wrote:
> > Venky Shankar wrote:
> > > Xiubo Li wrote:
> > > > When we are scrub r... - 01:16 PM Feature #56643: scrub: add one subcommand or option to add the missing objects back
- Xiubo Li wrote:
> Venky Shankar wrote:
> > Xiubo Li wrote:
> > > When we are scrub repairing the metadatas and som... - 01:32 PM Bug #56634: qa: workunit snaptest-intodir.sh fails with MDS crash
- Leaving this unassigned for now. Please bring this up if we hit this again.
- 01:21 PM Bug #57204 (Duplicate): MDLog.h: 99: FAILED ceph_assert(!segments.empty())
- ?
- 12:51 PM Bug #57204 (Triaged): MDLog.h: 99: FAILED ceph_assert(!segments.empty())
- 01:18 PM Bug #57072: Quincy 17.2.3 pybind/mgr/status: assert metadata failed
- Could you provide more info on how you ran into this. A reproducer would really help (or at least the debug mgr logs).
- 01:07 PM Bug #56261 (Triaged): crash: Migrator::import_notify_abort(CDir*, std::set<CDir*, std::less<CDir*...
- 01:06 PM Bug #56288 (Triaged): crash: Client::_readdir_cache_cb(dir_result_t*, int (*)(void*, dirent*, cep...
- 01:05 PM Bug #56697: qa: fs/snaps fails for fuse
- Seen in this quincy run as well https://pulpito.ceph.com/yuriw-2022-08-17_18:46:04-fs-wip-yuri7-testing-2022-08-17-09...
- 01:05 PM Bug #56592 (Triaged): mds: crash when mounting a client during the scrub repair is going on
- 01:02 PM Bug #56644 (Triaged): qa: test_rapid_creation fails with "No space left on device"
- 09:52 AM Bug #56644: qa: test_rapid_creation fails with "No space left on device"
- https://pulpito.ceph.com/yuriw-2022-08-18_23:16:33-fs-wip-yuri10-testing-2022-08-18-1400-pacific-distro-default-smith...
- 01:01 PM Bug #56698 (Triaged): client: FAILED ceph_assert(_size == 0)
- 01:00 PM Bug #57065 (Triaged): qa: test_query_client_ip_filter fails with latest 'perf stats' structure ch...
- 01:00 PM Bug #56988 (Triaged): mds: memory leak suspected
- 12:57 PM Bug #57084 (Triaged): Permissions of the .snap directory do not inherit ACLs
- 12:55 PM Bug #57087 (Triaged): qa: test_fragmented_injection (tasks.cephfs.test_data_scan.TestDataScan) fa...
- 12:53 PM Bug #57154 (Triaged): kernel/fuse client using ceph ID with uid restricted MDS caps cannot update...
- 12:47 PM Bug #57206 (Triaged): ceph_test_libcephfs_reclaim crashes during test
- 12:45 PM Bug #57210 (Triaged): NFS client unable to see newly created files when listing directory content...
- 12:43 PM Bug #57218 (Triaged): qa: tasks/{1-thrash/mds 2-workunit/cfuse_workunit_suites_fsstress}} fails
- 09:22 AM Bug #57218 (Triaged): qa: tasks/{1-thrash/mds 2-workunit/cfuse_workunit_suites_fsstress}} fails
- Seen in https://pulpito.ceph.com/yuriw-2022-08-18_23:16:33-fs-wip-yuri10-testing-2022-08-18-1400-pacific-distro-defau...
- 11:01 AM Backport #57201 (In Progress): pacific: snap_schedule: replace .snap with the client configured s...
- 10:57 AM Bug #46609: mds: CDir.cc: 956: FAILED ceph_assert(auth_pins == 0)
- Seen in recent pacific run: https://pulpito.ceph.com/yuriw-2022-08-19_21:01:11-fs-wip-yuri10-testing-2022-08-18-1400-...
- 10:09 AM Bug #57219 (Duplicate): qa: mds crashed while running workunit test fs/misc/dirfrag.sh
- This should be a know issue, please see https://tracker.ceph.com/issues/46609.
- 09:37 AM Bug #57219 (Duplicate): qa: mds crashed while running workunit test fs/misc/dirfrag.sh
- Seen in https://pulpito.ceph.com/yuriw-2022-08-19_21:01:11-fs-wip-yuri10-testing-2022-08-18-1400-pacific-distro-defau...
- 09:51 AM Bug #51964: qa: test_cephfs_mirror_restart_sync_on_blocklist failure
- Seen in this pacific run: https://pulpito.ceph.com/yuriw-2022-08-18_23:16:33-fs-wip-yuri10-testing-2022-08-18-1400-pa...
- 09:51 AM Bug #48773: qa: scrub does not complete
- Recent occurrence:
https://pulpito.ceph.com/yuriw-2022-08-18_23:16:33-fs-wip-yuri10-testing-2022-08-18-1400-pacifi... - 09:49 AM Bug #51267: CommandFailedError: Command failed (workunit test fs/snaps/snaptest-multiple-capsnaps...
- Recent occurence:
https://pulpito.ceph.com/yuriw-2022-08-18_23:16:33-fs-wip-yuri10-testing-2022-08-18-1400-pacific... - 09:17 AM Backport #56112 (Resolved): pacific: Test failure: test_flush (tasks.cephfs.test_readahead.TestRe...
- 09:17 AM Backport #56111 (Resolved): quincy: Test failure: test_flush (tasks.cephfs.test_readahead.TestRea...
- 09:17 AM Bug #55538 (Resolved): Test failure: test_flush (tasks.cephfs.test_readahead.TestReadahead)
- 08:55 AM Cleanup #4744 (Fix Under Review): mds: pass around LogSegments via std::shared_ptr
- PR: https://github.com/ceph/ceph/pull/47598
- 06:19 AM Backport #57042 (Resolved): quincy: pybind/mgr/volumes: interface to check the presence of subvol...
08/20/2022
- 01:33 AM Bug #54463 (Resolved): mds: flush mdlog if locked and still has wanted caps not satisfied
- 01:33 AM Backport #55756 (Resolved): quincy: mds: flush mdlog if locked and still has wanted caps not sati...
- 01:33 AM Cleanup #54362 (Resolved): client: do not release the global snaprealm until unmounting
- 01:32 AM Backport #55736 (Resolved): quincy: client: do not release the global snaprealm until unmounting
08/19/2022
- 11:00 PM Bug #57210: NFS client unable to see newly created files when listing directory contents in a FS ...
- I wonder if the real difference here is not the cloned subvolume, but whether the mount point had files in it prior t...
- 10:36 PM Bug #57210 (Resolved): NFS client unable to see newly created files when listing directory conten...
- Tried the following in a vstart cluster on ceph-main that launches ganesha v3.5 containers...
- 05:59 PM Bug #57206 (Rejected): ceph_test_libcephfs_reclaim crashes during test
- /a/vshankar-2022-08-18_04:30:42-fs-wip-vshankar-testing1-20220818-082047-testing-default-smithi/6978421
Core is at... - 05:51 PM Bug #57205 (Pending Backport): Test failure: test_subvolume_group_ls_filter_internal_directories ...
- /a/vshankar-2022-08-18_04:30:42-fs-wip-vshankar-testing1-20220818-082047-testing-default-smithi/6978395...
- 05:50 PM Bug #57204 (Duplicate): MDLog.h: 99: FAILED ceph_assert(!segments.empty())
- /a/vshankar-2022-08-18_04:30:42-fs-wip-vshankar-testing1-20220818-082047-testing-default-smithi/6978343
MDS crashe... - 04:41 PM Backport #55756: quincy: mds: flush mdlog if locked and still has wanted caps not satisfied
- Backport Bot wrote:
> https://github.com/ceph/ceph/pull/46494
merged - 02:58 PM Backport #56111: quincy: Test failure: test_flush (tasks.cephfs.test_readahead.TestReadahead)
- Dhairya Parmar wrote:
> https://github.com/ceph/ceph/pull/46899
merged - 02:53 PM Backport #55736: quincy: client: do not release the global snaprealm until unmounting
- Backport Bot wrote:
> https://github.com/ceph/ceph/pull/46495
merged - 01:28 PM Backport #57201 (Resolved): pacific: snap_schedule: replace .snap with the client configured snap...
- https://github.com/ceph/ceph/pull/47726
- 01:28 PM Backport #57200 (Resolved): quincy: snap_schedule: replace .snap with the client configured snap ...
- https://github.com/ceph/ceph/pull/47734
- 01:14 PM Bug #54283 (Resolved): qa/cephfs: is_mounted() depends on a mutable variable
- 01:14 PM Bug #55234 (Pending Backport): snap_schedule: replace .snap with the client configured snap dir name
- 01:10 PM Backport #57194 (Resolved): pacific: ceph pacific fails to perform fs/mirror test
- https://github.com/ceph/ceph/pull/48269
- 01:09 PM Backport #57193 (Resolved): quincy: ceph pacific fails to perform fs/mirror test
- https://github.com/ceph/ceph/pull/48268
- 01:03 PM Bug #55134 (Pending Backport): ceph pacific fails to perform fs/mirror test
08/18/2022
- 04:24 PM Bug #53192: High cephfs MDS latency and CPU load with snapshots and unlink operations
- This topic was discussed during the User + Dev meeting on Aug. 8th, 2022. One revelation that came of the meeting (as...
- 01:12 PM Bug #51964: qa: test_cephfs_mirror_restart_sync_on_blocklist failure
- Seen during weekly QA run - http://pulpito.front.sepia.ceph.com/rishabh-2022-07-24_08:53:36-fs-wip-rishabh-testing-20...
- 09:01 AM Bug #53724 (Fix Under Review): mds: stray directories are not purged when all past parents are clear
08/17/2022
- 01:09 PM Feature #16745: mon: prevent allocating snapids allocated for CephFS
- Greg, You mean to disable taking snaps for a pool if its in use with CephFS?
- 08:46 AM Backport #57156 (In Progress): quincy: cephfs-top: wrong/infinitely changing wsp values
- 05:47 AM Backport #57156 (Resolved): quincy: cephfs-top: wrong/infinitely changing wsp values
- https://github.com/ceph/ceph/pull/47648
- 08:42 AM Backport #57155 (In Progress): pacific: cephfs-top: wrong/infinitely changing wsp values
- 05:47 AM Backport #57155 (Resolved): pacific: cephfs-top: wrong/infinitely changing wsp values
- https://github.com/ceph/ceph/pull/47647
- 07:08 AM Backport #57158 (Resolved): quincy: doc: update snap-schedule notes regarding 'start' time
- https://github.com/ceph/ceph/pull/53577
- 07:08 AM Backport #57157 (Resolved): pacific: doc: update snap-schedule notes regarding 'start' time
- https://github.com/ceph/ceph/pull/53576
- 07:06 AM Documentation #56730 (Pending Backport): doc: update snap-schedule notes regarding 'start' time
- 05:44 AM Bug #56537 (Pending Backport): cephfs-top: wrong/infinitely changing wsp values
08/16/2022
- 08:53 PM Bug #57154: kernel/fuse client using ceph ID with uid restricted MDS caps cannot update caps
- This issue was first described in https://tracker.ceph.com/issues/56067#note-15
- 08:47 PM Bug #57154 (Pending Backport): kernel/fuse client using ceph ID with uid restricted MDS caps cann...
- A kclient sends cap updates as caller_uid:caller_gid 0:0. A fuse client sends cap updates as caller_uid:caller_gid -1...
- 08:51 PM Bug #56067: Cephfs data loss with root_squash enabled
- Created a separate tracker ticket for the cap updates being dropped for clients using ceph IDs with uid restricted MD...
- 02:41 PM Backport #57042: quincy: pybind/mgr/volumes: interface to check the presence of subvolumegroups/s...
- Backport Bot wrote:
> https://github.com/ceph/ceph/pull/47474
merged - 02:35 PM Backport #56112: pacific: Test failure: test_flush (tasks.cephfs.test_readahead.TestReadahead)
- Dhairya Parmar wrote:
> Venky Shankar wrote:
> > Dhairya, please do the backport.
>
> https://github.com/ceph/ce... - 02:31 PM Bug #56666: mds: standby-replay daemon always removed in MDSMonitor::prepare_beacon
- https://github.com/ceph/ceph/pull/47281 merged
- 02:07 PM Backport #56590: quincy: qa: iogen workunit: "The following counters failed to be set on mds daem...
- Ramana, please post the backport.
- 02:06 PM Backport #56541: quincy: crash: File "mgr/snap_schedule/module.py", in __init__: self.client = Sn...
- Milind, please take this one.
- 02:06 PM Bug #56269: crash: File "mgr/snap_schedule/module.py", in __init__: self.client = SnapSchedClient...
- Venky Shankar wrote:
> Milind, please take this one.
Sorry - I meant to update the backport tracker. - 02:04 PM Bug #56269: crash: File "mgr/snap_schedule/module.py", in __init__: self.client = SnapSchedClient...
- Milind, please take this one.
- 02:05 PM Backport #56542: pacific: crash: File "mgr/snap_schedule/module.py", in __init__: self.client = S...
- Milind, please take this one.
- 01:46 PM Bug #50224: qa: test_mirroring_init_failure_with_recovery failure
- This is seen recently in https://pulpito.ceph.com/yuriw-2022-08-11_16:57:01-fs-wip-yuri3-testing-2022-08-11-0809-paci...
- 04:20 AM Bug #56249 (Fix Under Review): crash: int Client::_do_remount(bool): abort
08/15/2022
- 03:21 PM Backport #56978: pacific: mgr/volumes: Subvolume creation failed on FIPs enabled system
- Backport Bot wrote:
> https://github.com/ceph/ceph/pull/47369
merged - 12:27 PM Bug #50834 (Resolved): MDS heartbeat timed out between during executing MDCache::start_files_to_r...
- 12:27 PM Backport #50914 (Resolved): octopus: MDS heartbeat timed out between during executing MDCache::st...
- 12:26 PM Bug #52123 (Resolved): mds sends cap updates with btime zeroed out
- 12:26 PM Backport #52635 (Resolved): pacific: mds sends cap updates with btime zeroed out
- 12:26 PM Backport #52634 (Resolved): octopus: mds sends cap updates with btime zeroed out
- 12:26 PM Bug #48422 (Resolved): mds: MDCache.cc:5319 FAILED ceph_assert(rejoin_ack_gather.count(mds->get_n...
- 12:26 PM Backport #51933 (Resolved): octopus: mds: MDCache.cc:5319 FAILED ceph_assert(rejoin_ack_gather.co...
- 12:25 PM Bug #48231 (Resolved): qa: test_subvolume_clone_in_progress_snapshot_rm is racy
- 12:25 PM Backport #51201 (Resolved): octopus: qa: test_subvolume_clone_in_progress_snapshot_rm is racy
- 12:23 PM Bug #41072 (Resolved): scheduled cephfs snapshots (via ceph manager)
- 12:23 PM Backport #47200 (Rejected): octopus: scheduled cephfs snapshots (via ceph manager)
- 12:22 PM Bug #53952 (Resolved): mds: mds_oft_prefetch_dirfrags default to false
- 12:21 PM Backport #54194 (Resolved): pacific: mds: mds_oft_prefetch_dirfrags default to false
- 12:21 PM Backport #54196 (Resolved): quincy: mds: mds_oft_prefetch_dirfrags default to false
- 12:21 PM Backport #54195 (Resolved): octopus: mds: mds_oft_prefetch_dirfrags default to false
- 12:21 PM Bug #53805 (Resolved): mds: seg fault in expire_recursive
- 12:21 PM Backport #54407 (Resolved): quincy: mds: seg fault in expire_recursive
- 12:20 PM Backport #54220 (Resolved): pacific: mds: seg fault in expire_recursive
- 12:20 PM Backport #54219 (Resolved): octopus: mds: seg fault in expire_recursive
- 09:35 AM Bug #56249 (In Progress): crash: int Client::_do_remount(bool): abort
- 09:35 AM Bug #56249: crash: int Client::_do_remount(bool): abort
- Went through the kernel code I couldn't find any case in our case could cause the failure.
And from https://tracke... - 07:05 AM Bug #56249: crash: int Client::_do_remount(bool): abort
- Xiubo Li wrote:
> This only exist in the **v17.1.0** and the logic has been changed after [1][2][3] below. When tryi... - 06:16 AM Bug #56249: crash: int Client::_do_remount(bool): abort
- This only exist in the **v17.1.0** and the logic has been changed after [1][2][3] below. When trying remount to inval...
- 06:04 AM Bug #56249: crash: int Client::_do_remount(bool): abort
- Venky,
Please check this one https://tracker.ceph.com/issues/56532. It should be the same bug with this one. - 07:18 AM Bug #57126 (Fix Under Review): client: abort the client daemons when we couldn't invalidate the d...
- 07:12 AM Bug #57126 (Resolved): client: abort the client daemons when we couldn't invalidate the dentry ca...
- It was introduced by https://tracker.ceph.com/issues/54049.
From the options:... - 05:54 AM Bug #54653: crash: uint64_t CephFuse::Handle::fino_snap(uint64_t): assert(stag_snap_map.count(stag))
- I found one case could cause this, such as in the xfstests-dev's open_by_handle.c, which will use the name_to_handle_...
- 05:53 AM Bug #56380: crash: Client::_get_vino(Inode*)
- I found one case could cause this, such as in the xfstests-dev's open_by_handle.c, which will use the name_to_handle_...
- 05:52 AM Bug #56774: crash: Client::_get_vino(Inode*)
- I found one case could cause this, such as in the xfstests-dev's open_by_handle.c, which will use the name_to_handle_...
- 05:18 AM Bug #56774 (Duplicate): crash: Client::_get_vino(Inode*)
- 05:52 AM Bug #56263: crash: Client::_get_vino(Inode*)
- I found one case could cause this, such as in the xfstests-dev's open_by_handle.c, which will use the name_to_handle_...
08/12/2022
- 05:22 PM Documentation #57062: Document access patterns that have good/pathological performance on CephFS
- I think that a good place for this info to be added would be https://docs.ceph.com/en/quincy/cephfs/app-best-practice...
- 12:03 PM Documentation #57115 (New): Explanation for cache pressure
- Following up on the "thread":https://lists.ceph.io/hyperkitty/list/ceph-users@ceph.io/thread/DOUQNI5YQ74YB3FS5ZOQI2MS...
- 09:54 AM Bug #56996: Transient data read corruption from other machine
- Confirmed with Venky, when the **CInode::filelock** is in **LOCK_MIX** state we won't guarantee the data consistency ...
- 09:31 AM Feature #40633 (Resolved): mds: dump recent log events for extraordinary events
- 09:23 AM Backport #57113 (Resolved): pacific: Intermittent ParsingError failure in mgr/volumes module dur...
- https://github.com/ceph/ceph/pull/47112
- 09:23 AM Backport #57112 (In Progress): quincy: Intermittent ParsingError failure in mgr/volumes module d...
- https://github.com/ceph/ceph/pull/47747
- 09:12 AM Bug #55583 (Pending Backport): Intermittent ParsingError failure in mgr/volumes module during "c...
- 09:11 AM Backport #57111 (Resolved): quincy: mds: handle deferred client request core when mds reboot
- https://github.com/ceph/ceph/pull/53363
- 09:11 AM Backport #57110 (Resolved): pacific: mds: handle deferred client request core when mds reboot
- https://github.com/ceph/ceph/pull/53362
- 09:10 AM Bug #56116 (Pending Backport): mds: handle deferred client request core when mds reboot
- 05:54 AM Bug #54460: snaptest-multiple-capsnaps.sh test failure
- Milind Changire wrote:
> client-type: fuse
>
> * Iteratively running shell scripts under *qa/workunits/fs/snaps/*...
08/11/2022
- 04:08 PM Bug #57048: osdc/Journaler: better handle ENOENT during replay as up:standby-replay
- Greg Farnum wrote:
> Patrick Donnelly wrote:
> > Venky Shankar wrote:
> > > Patrick,
> > >
> > > Do you mean a ... - 03:12 PM Bug #57048: osdc/Journaler: better handle ENOENT during replay as up:standby-replay
- Patrick Donnelly wrote:
> Venky Shankar wrote:
> > Patrick,
> >
> > Do you mean a standby-replay MDS should tole... - 01:37 PM Bug #57048: osdc/Journaler: better handle ENOENT during replay as up:standby-replay
- Venky Shankar wrote:
> Patrick,
>
> Do you mean a standby-replay MDS should tolerate missing journal objects?
... - 01:40 PM Backport #51337 (Rejected): nautilus: mds: avoid journaling overhead for setxattr("ceph.dir.subvo...
- 06:56 AM Bug #57087: qa: test_fragmented_injection (tasks.cephfs.test_data_scan.TestDataScan) failure
- Note that the test successfully passed on the re-run
https://pulpito.ceph.com/yuriw-2022-08-10_20:34:29-fs-wip-yuri6... - 03:44 AM Bug #54253: Avoid OOM exceeding 10x MDS cache limit on restart after many files were opened
- Unfortunately I must report that I'm still hitting this issue even with Ceph 16.2.7 and...
08/10/2022
- 05:30 PM Feature #56140 (Fix Under Review): cephfs: tooling to identify inode (metadata) corruption
- 05:20 PM Feature #57091 (Resolved): mds: modify scrub to catch dentry corruption
- Such as "first" snapshot being an invalid value.
- 05:01 PM Feature #57090 (Resolved): MDSMonitor,mds: add MDSMap flag to prevent clients from connecting
- During some recovery situations, it would be useful to have MDS up but prevent clients from establishing sessions. Us...
- 03:18 PM Backport #56979: quincy: mgr/volumes: Subvolume creation failed on FIPs enabled system
- Backport Bot wrote:
> https://github.com/ceph/ceph/pull/47368
mergedReviewed-by: Ramana Raja <rraja@redhat.com>
- 02:34 PM Bug #55216 (Resolved): cephfs-shell: creates directories in local file system even if file not found
- PR along with backport PRs merged. Marking as resolved.
- 02:30 PM Backport #55627 (Resolved): pacific: cephfs-shell: creates directories in local file system even ...
- merged
- 01:59 PM Feature #55715 (Resolved): pybind/mgr/cephadm/upgrade: allow upgrades without reducing max_mds
- 11:13 AM Bug #54271: mds/OpenFileTable.cc: 777: FAILED ceph_assert(omap_num_objs == num_objs)
- We will wait for this to happen in recent versions.
- 11:11 AM Bug #54271: mds/OpenFileTable.cc: 777: FAILED ceph_assert(omap_num_objs == num_objs)
- Lowering the priority as this is seen only in nautilus and not seen in supported versions.
- 10:48 AM Bug #56644: qa: test_rapid_creation fails with "No space left on device"
- https://pulpito.ceph.com/yuriw-2022-08-04_20:54:08-fs-wip-yuri6-testing-2022-08-04-0617-pacific-distro-default-smithi...
- 10:35 AM Bug #57087 (Pending Backport): qa: test_fragmented_injection (tasks.cephfs.test_data_scan.TestDat...
- Seen in https://pulpito.ceph.com/yuriw-2022-08-04_20:54:08-fs-wip-yuri6-testing-2022-08-04-0617-pacific-distro-defaul...
- 10:01 AM Bug #51276 (Resolved): mds: avoid journaling overhead for setxattr("ceph.dir.subvolume") for no-o...
- 10:00 AM Backport #51337 (Resolved): nautilus: mds: avoid journaling overhead for setxattr("ceph.dir.subvo...
- Nautilus is EOL
- 09:49 AM Bug #51267: CommandFailedError: Command failed (workunit test fs/snaps/snaptest-multiple-capsnaps...
- Seen in https://pulpito.ceph.com/yuriw-2022-08-04_20:54:08-fs-wip-yuri6-testing-2022-08-04-0617-pacific-distro-defaul...
- 08:18 AM Bug #57083 (Fix Under Review): ceph-fuse: monclient(hunting): handle_auth_bad_method server allow...
- 07:56 AM Bug #57083: ceph-fuse: monclient(hunting): handle_auth_bad_method server allowed_methods [2] but ...
- The **nautilus** is using **python2**, while the **pacific** qa suite is using **python3** and the qa test suite seem...
- 07:37 AM Bug #57083: ceph-fuse: monclient(hunting): handle_auth_bad_method server allowed_methods [2] but ...
- From **remote/smithi029/log/ceph-mon.a.log.gz**: ...
- 07:26 AM Bug #57083: ceph-fuse: monclient(hunting): handle_auth_bad_method server allowed_methods [2] but ...
- The root cause is that in **nautilus** the **qa/workunits/fs/upgrade/volume_client** script is using **python2** to r...
- 07:21 AM Bug #57083: ceph-fuse: monclient(hunting): handle_auth_bad_method server allowed_methods [2] but ...
- From **remote/smithi029/log/ceph-mon.a.log.gz**: ...
- 07:10 AM Bug #57083 (Resolved): ceph-fuse: monclient(hunting): handle_auth_bad_method server allowed_metho...
- From https://pulpito.ceph.com/yuriw-2022-07-24_15:34:38-fs-wip-yuri2-testing-2022-07-15-0755-pacific-distro-default-s...
- 07:54 AM Bug #53360 (Duplicate): pacific: client: "handle_auth_bad_method server allowed_methods [2] but i...
- Missed this existing tracker. Will track this in https://tracker.ceph.com/issues/57083 tracker. Have found root cause...
- 07:37 AM Bug #57084 (Resolved): Permissions of the .snap directory do not inherit ACLs
- when using CephFS with POSIX ACLs I noticed that the .snap directory does not inherit the ACLs from its parent but on...
- 07:26 AM Backport #53861: pacific: qa: tasks.cephfs.fuse_mount:mount command failed
- Created a new tracker to fix it https://tracker.ceph.com/issues/57083.
- 06:50 AM Backport #53861: pacific: qa: tasks.cephfs.fuse_mount:mount command failed
- Xiubo Li wrote:
> Kotresh Hiremath Ravishankar wrote:
> > Xiubo,
> >
> > Looks like this is seen again in this p... - 07:23 AM Bug #55572: qa/cephfs: omit_sudo doesn't have effect when passed to run_shell()
- I think this needs to be backported. Nikhil mentioned that the PR https://github.com/ceph/ceph/pull/47112 in pacific ...
- 07:09 AM Bug #51282: pybind/mgr/mgr_util: .mgr pool may be created too early causing spurious PG_DEGRADED ...
- Seen in recent quincy run
https://pulpito.ceph.com/yuriw-2022-08-04_11:54:20-fs-wip-yuri8-testing-2022-08-0... - 07:08 AM Bug #57071 (Fix Under Review): mds: consider mds_cap_revoke_eviction_timeout for get_late_revokin...
08/09/2022
- 04:13 PM Backport #56527: pacific: mds: src/mds/MDLog.cc: 283: FAILED ceph_assert(!mds->is_ any_replay())
- Backport Bot wrote:
> https://github.com/ceph/ceph/pull/47111
merged - 04:12 PM Backport #56152: pacific: mgr/snap_schedule: schedule updates are not persisted across mgr restart
- https://github.com/ceph/ceph/pull/46797 merged
- 12:55 PM Bug #56529: ceph-fs crashes on getfattr
- Frank Schilder wrote:
> Thanks for the quick answer. Then, I guess, the patch to the ceph-fs clients will handle thi... - 12:54 PM Bug #56529: ceph-fs crashes on getfattr
- Frank Schilder wrote:
> Thanks for the quick answer. Then, I guess, the patch to the ceph-fs clients will handle thi... - 12:47 PM Bug #56529: ceph-fs crashes on getfattr
- Thanks for the quick answer. Then, I guess, the patch to the ceph-fs clients will handle this once it is approved? I ...
- 12:40 PM Bug #56529: ceph-fs crashes on getfattr
- Frank Schilder wrote:
> Hi all,
>
> this story continues, this time with a _valid_ vxattr name. I just observed e... - 12:33 PM Bug #56529: ceph-fs crashes on getfattr
- Hi all,
this story continues, this time with a _valid_ vxattr name. I just observed exactly the same problem now w... - 11:40 AM Bug #57072 (Pending Backport): Quincy 17.2.3 pybind/mgr/status: assert metadata failed
- `ceph fs status` return AssertionError
Error EINVAL: Traceback (most recent call last):
File "/usr/share/ceph/m... - 10:24 AM Backport #53861: pacific: qa: tasks.cephfs.fuse_mount:mount command failed
- Kotresh Hiremath Ravishankar wrote:
> Xiubo,
>
> Looks like this is seen again in this pacific run ?
>
> https... - 10:13 AM Backport #53861: pacific: qa: tasks.cephfs.fuse_mount:mount command failed
- Xiubo,
Looks like this is seen again in this pacific run ?
https://pulpito.ceph.com/yuriw-2022-07-24_15:34:38-f... - 10:24 AM Bug #56644: qa: test_rapid_creation fails with "No space left on device"
- Seen in recent pacific run https://pulpito.ceph.com/yuriw-2022-07-24_15:34:38-fs-wip-yuri2-testing-2022-07-15-0755-pa...
- 09:27 AM Bug #57071 (Fix Under Review): mds: consider mds_cap_revoke_eviction_timeout for get_late_revokin...
- Even though mds_cap_revoke_eviction_timeout is set to zero, ceph-mon reports some clients failing to respond to capab...
- 09:01 AM Bug #57048: osdc/Journaler: better handle ENOENT during replay as up:standby-replay
- Patrick,
Do you mean a standby-replay MDS should tolerate missing journal objects? How can it end up in such a sit... - 08:58 AM Bug #56808: crash: LogSegment* MDLog::get_current_segment(): assert(!segments.empty())
- Looks similar to https://tracker.ceph.com/issues/51589 which was fixed a while ago.
Kotresh, please RCA this. - 08:16 AM Backport #57058 (In Progress): pacific: mgr/volumes: Handle internal metadata directories under '...
- 08:06 AM Backport #57057 (In Progress): quincy: mgr/volumes: Handle internal metadata directories under '/...
- 07:07 AM Bug #54462: Command failed (workunit test fs/snaps/snaptest-git-ceph.sh) on smithi055 with status...
- This maybe duplicated to https://tracker.ceph.com/issues/55332.
- 06:55 AM Bug #54462: Command failed (workunit test fs/snaps/snaptest-git-ceph.sh) on smithi055 with status...
- Seen in this run too.
https://pulpito.ceph.com/yuriw-2022-08-02_21:20:37-fs-wip-yuri7-testing-2022-07-27-0808-quin... - 06:51 AM Bug #56592: mds: crash when mounting a client during the scrub repair is going on
- More info:
I was just simulating the cu case we hit by just removing one object of the directory from the metadata... - 06:47 AM Bug #56592: mds: crash when mounting a client during the scrub repair is going on
- Venky Shankar wrote:
> Xiubo,
>
> Were you trying to mount /mydir when it was getting repaired?
No, I was just... - 06:23 AM Bug #56592: mds: crash when mounting a client during the scrub repair is going on
- Xiubo,
Were you trying to mount /mydir when it was getting repaired? - 06:47 AM Bug #51964: qa: test_cephfs_mirror_restart_sync_on_blocklist failure
- Seen in this quincy run https://pulpito.ceph.com/yuriw-2022-08-02_21:20:37-fs-wip-yuri7-testing-2022-07-27-0808-quinc...
- 06:30 AM Bug #56830: crash: cephfs::mirror::PeerReplayer::pick_directory()
- Dhairya,
Please take a look at this. I think there is some sort of race that is causing this crash while iterating... - 06:25 AM Bug #57014: cephfs-top: add an option to dump the computed values to stdout
- Jos, please take this one.
- 05:54 AM Bug #56996 (In Progress): Transient data read corruption from other machine
- 04:48 AM Bug #56996: Transient data read corruption from other machine
- Witold Baryluk wrote:
> Ok. I still do not understand why this can happen:
>
> writer: write("a"); write("b"); wr... - 04:59 AM Bug #57065 (Closed): qa: test_query_client_ip_filter fails with latest 'perf stats' structure cha...
- test_query_client_ip_filter fails with the below error in tests [1] and [2]. This happens when PR [3] is tested.
<... - 04:41 AM Bug #57064 (Need More Info): qa: test_add_ancestor_and_child_directory failure
- Seen in recent quincy run https://pulpito.ceph.com/yuriw-2022-08-04_11:54:20-fs-wip-yuri8-testing-2022-08-03-1028-qui...
- 02:47 AM Bug #56067: Cephfs data loss with root_squash enabled
- Patrick Donnelly wrote:
> Please open a PR for discussion.
https://github.com/ceph/ceph/pull/47506 . Please take ... - 02:45 AM Bug #56067 (Fix Under Review): Cephfs data loss with root_squash enabled
08/08/2022
- 08:56 PM Bug #51282: pybind/mgr/mgr_util: .mgr pool may be created too early causing spurious PG_DEGRADED ...
- /a/yuriw-2022-08-04_11:58:29-rados-wip-yuri3-testing-2022-08-03-0828-pacific-distro-default-smithi/6958108
- 07:03 PM Documentation #57062 (New): Document access patterns that have good/pathological performance on C...
- I have a CephFS 16.2.7 with 200 M small files (between 1 KB and 100 KB; ther are a few larger ones up to 200 MB) and ...
- 03:28 PM Bug #56048: ceph.mirror.info is not removed from target FS when mirroring is disabled
- Hi Venky,
I tried it again, now with 17.2.1, and I could reproduce the issue. The mgr debug log is below.
As fa... - 01:08 PM Bug #56048: ceph.mirror.info is not removed from target FS when mirroring is disabled
- Andreas Teuchert wrote:
> When disabling mirroring on a FS with "ceph fs snapshot mirror disable <source-fs>" the "c... - 02:32 PM Bug #56996: Transient data read corruption from other machine
- Ok. I still do not understand why this can happen:
writer: write("a"); write("b"); write("c");
reader (other cl... - 06:33 AM Bug #56996: Transient data read corruption from other machine
- Witold Baryluk wrote:
> What about when there is one writer and one reader?
This will depend on whether they are ... - 01:18 PM Feature #56643: scrub: add one subcommand or option to add the missing objects back
- Venky Shankar wrote:
> Xiubo Li wrote:
> > When we are scrub repairing the metadatas and some objects may get lost ... - 01:02 PM Feature #56643: scrub: add one subcommand or option to add the missing objects back
- Xiubo Li wrote:
> When we are scrub repairing the metadatas and some objects may get lost due to some reasons. After... - 01:01 PM Bug #56249: crash: int Client::_do_remount(bool): abort
- Xiubo Li wrote:
> Should be fixed by https://tracker.ceph.com/issues/54049.
Looks the same. However, I'm not sure... - 09:41 AM Bug #56506: pacific: Test failure: test_rebuild_backtraceless (tasks.cephfs.test_data_scan.TestDa...
- Milind Changire wrote:
> Adding any more condition to the assertion expression and passing the assertion is not goin... - 08:07 AM Bug #56506: pacific: Test failure: test_rebuild_backtraceless (tasks.cephfs.test_data_scan.TestDa...
- Adding any more condition to the assertion expression and passing the assertion is not going to do any good.
Since M... - 05:37 AM Bug #56506: pacific: Test failure: test_rebuild_backtraceless (tasks.cephfs.test_data_scan.TestDa...
- Never mind - I see the err coming from JournalPointer. If the MDS is respawning/shutting down could that condition ad...
- 05:29 AM Bug #56506: pacific: Test failure: test_rebuild_backtraceless (tasks.cephfs.test_data_scan.TestDa...
- Milind Changire wrote:
> This seems to be a race between an mds respawn and the MDLog::_recovery_thread()
> In Paci... - 08:55 AM Backport #57058 (Resolved): pacific: mgr/volumes: Handle internal metadata directories under '/vo...
- https://github.com/ceph/ceph/pull/47512
- 08:55 AM Backport #57057 (Resolved): quincy: mgr/volumes: Handle internal metadata directories under '/vol...
- https://github.com/ceph/ceph/pull/47511
- 08:54 AM Bug #55762 (Pending Backport): mgr/volumes: Handle internal metadata directories under '/volumes'...
Also available in: Atom